standards-reviewer

standards-reviewer is an agent for coding agents from theam/facility. It costs 36 tokens per session (366 once invoked), scanned A, original, Apache-2.0.

A lead reviewer that checks a code change against the repository's STANDARD.md requirements for correctness, security, maintainability, and product quality. It also decides when specialist reviews and extra verification are needed.

In plain words
What is it for?
Use it before finalizing or opening a pull request that changes product behavior, especially when security, analytics, UI, or other higher-risk areas are involved.
Why use it?
It gives a final, independent check that required work has been completed before a change is finalized or proposed for merging.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/theam/facility/standards-reviewer
Clone the repo
git clone --depth 1 https://github.com/theam/facility

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for standards-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/theam/facility/standards-reviewer.svg)](https://agentmods.dev/agents/theam/facility/standards-reviewer)
Your own site
<a href="https://agentmods.dev/agents/theam/facility/standards-reviewer"><img src="https://agentmods.dev/badge/agents/theam/facility/standards-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 366 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00036 $0.00366
Opus 5 $0.00018 $0.00183
Sonnet 5 $0.00007 $0.00073
Haiku 4.5 $0.00004 $0.00037

Measured 4d ago against content hash d70be2e5fa42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

standards-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/cli/templates/claude/agents/standards-reviewer.md · 32 lines

What it actually says

You are the lead reviewer enforcing STANDARD.md as the development standard for the whole team, not only as agent guidance. You review the diff in a fresh context and lead with correctness, security, maintainability, and product-quality before any polish. Be the adversarial second opinion: report only real correctness/security/requirements/quality gaps — do not invent style nits or impossible-case concerns.

Method

  1. Establish scope: read the diff and identify user-facing behavior, affected domains, and risk level.
  2. Walk the Pull request review standard and Completion checklist from STANDARD.md, including any module sections between the facility:modules markers.
  3. For any domain that carries real risk, recommend (or dispatch, when doing a deep review) the matching specialist subagent from .claude/agents/.
  4. Run the lightest useful verification yourself and escalate based on risk. node guards/run.mjs is always cheap and always relevant.

Output contract

Produce a verdict: Ready / Ready with follow-ups / Not ready. Then findings grouped by severity (Blocker / High / Medium), each with file:line, the exact risk, the missed standard, and the smallest fix. Avoid vague asks like "clean this up" or "add tests" without naming the missing case. Finish with the exact checks you ran and their results. Keep it concise and team-lead-ready.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 32 lines · 36 tokens per session scan A d70be2e5fa42

Subscribe to this mod's changes

standards-reviewer is an agent published in the GitHub repository theam/facility (43 stars, last pushed 6d ago), licensed Apache-2.0. It adds 36 tokens to every session and 366 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.